Learning to Caricature via Semantic Shape Transform
arXiv:2008.05090
Abstract
Caricature is an artistic drawing created to abstract or exaggerate facial features of a person. Rendering visually pleasing caricatures is a difficult task that requires professional skills, and thus it is of great interest to design a method to automatically generate such drawings. To deal with large shape changes, we propose an algorithm based on a semantic shape transform to produce diverse and plausible shape exaggerations. Specifically, we predict pixel-wise semantic correspondences and perform image warping on the input photo to achieve dense shape transformation. We show that the proposed framework is able to render visually pleasing shape exaggerations while maintaining their facial structures. In addition, our model allows users to manipulate the shape via the semantic map. We demonstrate the effectiveness of our approach on a large photograph-caricature benchmark dataset with comparisons to the state-of-the-art methods.
Submitted to IJCV, code and model are available at https://github.com/wenqingchu/Semantic-CariGANs/
References in corpus (10)
- Toward Multimodal Image-to-Image Translation
- Deformable Convolutional Networks
- Texture Synthesis Using Convolutional Neural Networks
- Multimodal Unsupervised Image-to-Image Translation
- Demystifying Neural Style Transfer
- StyleBank: An Explicit Representation for Neural Image Style Transfer
- WebCaricature: a benchmark for caricature recognition
- Transformation-Grounded Image Generation Network for Novel 3D View Synthesis
- Diversified Texture Synthesis with Feed-forward Networks
- CariGAN: Caricature Generation through Weakly Paired Adversarial Learning